|
Tao Lu 鲁涛
|
I received my PhD from Nanjing University in 2023, supervised by Prof. Gangshan Wu and Prof. Limin Wang. My research focuses on perceiving and understanding the 3D world through both semantic and geometric approaches. Currently, I am engaged in research on general and user-friendly novel view rendering methods at the Shanghai AI Lab. My long-term goal is to integrate these insights and methods into a robot to enhance its interaction with the world.
|
Publications
Octree-GS: Towards Consistent Real-time Rendering with LOD-Structured 3D Gaussians
|
||
GSDF: 3DGS Meets SDF for Improved Rendering and Reconstruction
|
||
Scaffold-GS: Structured 3D Gaussians for View-Adaptive Rendering
|
||
LinK: Linear Kernel for LiDAR-based 3D Perception
|
||
Learning Optical Flow and Scene Flow with Bidirectional Camera-LiDAR Fusion
|
||
APP-Net: Auxiliary-Point-Based Push and Pull Operations for Efficient Point Cloud Recognition
|
||
SparseBEV: High-Performance Sparse 3D Object Detection from Multi-Camera Videos
|
||
CamLiFlow: Bidirectional camera-LiDAR fusion for joint optical flow and scene flow estimation
|
||
CGA-Net: Category Guided Aggregation for Point Cloud Semantic Segmentation
|
Activities
Reviewer : CVPR, ICCV, AAAI, TPAMI, IJCV...
Design and source code from Kaiming He. |